Docking and Scoring Function Benchmarks
- BigBind and BayesBind: BigBind: Learning from Nonstructural Data for Structure-Based Virtual Screening
- CASF: CASF offers benchmark packages for the assessment of scoring functions, with versions CASF-2016, CASF-2013, and CASF-2007 available for download upon registration.
- D-COID: Dataset of Congruent Inhibitors and Decoys
- DEKOIS: Provides DEKOIS 2.0, a library of benchmark data sets for objective in silico screening.
- Disco: A default benchmark containing 95 targets selected from the DUD-E Targets list for docking datasets generation.
- Lit-PCBA: A dataset for virtual screening and machine learning with 15 target sets, 7761 actives, and 382674 unique inactives selected from high-confidence PubChem Bioassay data.
- MF-PCBA: A repository containing code for downloading, filtering, and assembling the MF-PCBA datasets for machine learning in drug discovery.
- MUDB-DecoyMaker2.0: A Python GUI application to generate maximal unbiased benchmarking sets data sets for virtual drug screening.
- TocoDDB: Topology-Based and Conformation-Based Decoys Database: An Unbiased Online Database for Training and Benchmarking Machine-Learning Scoring Functions
- TocoDecoy: A new approach to design unbiased datasets for training and benchmarking machine-learning scoring functions.
- Uni-Dock-Benchmarks:
